Hindsight for Foresight: Unsupervised Structured Dynamics Models from Physical Interaction
Iman Nematollahi,Oier Mees,Lukas Hermann,Wolfram Burgard,Iman Nematollahi,Oier Mees,Lukas Hermann,Wolfram Burgard
A key challenge for an agent learning to interact with the world is to reason about physical properties of objects and to foresee their dynamics under the effect of applied forces. In order to scale learning through interaction to many objects and scenes, robots should be able to improve their own performance from real-world experience without requiring human supervision. To this end, we propose a...
